001    /*
002     * Copyright (c) 2007-2015 Concurrent, Inc. All Rights Reserved.
003     *
004     * Project and contact information: http://www.cascading.org/
005     *
006     * This file is part of the Cascading project.
007     *
008     * Licensed under the Apache License, Version 2.0 (the "License");
009     * you may not use this file except in compliance with the License.
010     * You may obtain a copy of the License at
011     *
012     *     http://www.apache.org/licenses/LICENSE-2.0
013     *
014     * Unless required by applicable law or agreed to in writing, software
015     * distributed under the License is distributed on an "AS IS" BASIS,
016     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
017     * See the License for the specific language governing permissions and
018     * limitations under the License.
019     */
020    
021    package cascading.operation.regex;
022    
023    import java.beans.ConstructorProperties;
024    import java.util.regex.Matcher;
025    
026    import cascading.flow.FlowProcess;
027    import cascading.operation.Function;
028    import cascading.operation.FunctionCall;
029    import cascading.operation.OperationCall;
030    import cascading.tuple.Fields;
031    import cascading.tuple.Tuple;
032    import cascading.util.Pair;
033    
034    /**
035     * Class RegexGenerator will emit a new Tuple for every matched regex group.
036     * <p/>
037     * Note a {@code null} valued argument passed to the parser will be converted to an empty string ({@code ""}) before
038     * the regex is applied.
039     * <p/>
040     * Any Object value will be coerced to a String type if type information is provided. See the
041     * {@link cascading.tuple.type.CoercibleType} interface to control how custom Object types are converted to String
042     * values.
043     */
044    public class RegexGenerator extends RegexOperation<Pair<Matcher, Tuple>> implements Function<Pair<Matcher, Tuple>>
045      {
046      /**
047       * Constructor RegexGenerator creates a new RegexGenerator instance.
048       *
049       * @param patternString of type String
050       */
051      @ConstructorProperties({"patternString"})
052      public RegexGenerator( String patternString )
053        {
054        super( 1, Fields.size( 1 ), patternString );
055        }
056    
057      /**
058       * Constructor RegexGenerator creates a new RegexGenerator instance.
059       *
060       * @param fieldDeclaration of type Fields
061       * @param patternString    of type String
062       */
063      @ConstructorProperties({"fieldDeclaration", "patternString"})
064      public RegexGenerator( Fields fieldDeclaration, String patternString )
065        {
066        super( 1, fieldDeclaration, patternString );
067    
068        if( fieldDeclaration.size() != 1 )
069          throw new IllegalArgumentException( "fieldDeclaration may only declare one field, was " + fieldDeclaration.print() );
070        }
071    
072      @Override
073      public void prepare( FlowProcess flowProcess, OperationCall<Pair<Matcher, Tuple>> operationCall )
074        {
075        operationCall.setContext( new Pair<Matcher, Tuple>( getPattern().matcher( "" ), Tuple.size( 1 ) ) );
076        }
077    
078      @Override
079      public void operate( FlowProcess flowProcess, FunctionCall<Pair<Matcher, Tuple>> functionCall )
080        {
081        String value = functionCall.getArguments().getString( 0 );
082    
083        if( value == null )
084          value = "";
085    
086        Matcher matcher = functionCall.getContext().getLhs().reset( value );
087    
088        while( matcher.find() )
089          {
090          functionCall.getContext().getRhs().set( 0, matcher.group() );
091          functionCall.getOutputCollector().add( functionCall.getContext().getRhs() );
092          }
093        }
094      }